Systems and methods for voice assistant for electronic health records

Abstract

An electronic record voice assistant system can include one or more processors that receive audio data, apply a machine learning model to the audio data to generate speech data including at least one value, determine a state of an electronic record, and update one or more fields of the electronic record using the state and the at least one value.

What is claimed is: 
     
       1. A method of integrating an electronic voice assistant with electronic records, comprising:
 applying, by the one or more processors, a speech model to audio data to generate speech data; 
 determining, by the one or more processors, a state of an electronic record, the electronic record comprising at least one of an electronic health record, an electronic medical record, an electronic dental record, a practice management system record, or a treatment plan record, the electronic record including a plurality of fields, the state comprising selected field in the electronic record; 
 generating, by the one or more processors, based on the speech data, at least a first phrase representing the speech data and a second phrase representing the speech data; 
 determining, by the one or more processors, a first confidence value of the first phrase associated with spatial relationships between the plurality of fields of the electronic record and the state; 
 determining, by the one or more processors, a second confidence value of the second phrase associated with the spatial relationships between the plurality of fields of the electronic record and the state; 
 determining, by the one or more processors, a command for navigation of the electronic record to be the first phrase responsive to the first confidence value being greater than the second confidence value; 
 assigning, by the one or more processors, at least one value of the speech data to a particular field of the plurality of fields based on the command and the state. 
 
     
     
       2. The method of  claim 1 , comprising updating, by the one or more processors, the state responsive to assigning the at least one value. 
     
     
       3. The method of  claim 1 , comprising identifying, by the one or more processors, the particular field using the command. 
     
     
       4. The method of  claim 1 , comprising applying, by the one or more processors, at least one of text recognition or computer vision to an image representing the electronic record to determine the state. 
     
     
       5. The method of  claim 4 , comprising generating a data object representing the electronic record responsive to applying the least one of text recognition or computer vision to the image. 
     
     
       6. The method of  claim 1 , comprising applying, by the one or more processors, a signal indicative of at least one of a mouse movement or a keystroke to a client device to assign the at least one value to the particular field. 
     
     
       7. The method of  claim 1 , wherein the one or more processors include a first processor operating on a client device and a second processor operating on a server device. 
     
     
       8. The method of  claim 1 , comprising applying, by the one or more processors, the state as input to the speech model to cause the speech model to generate the speech data based on the state. 
     
     
       9. The method of  claim 1 , comprising determining, by the one or more processors, that the at least one value corresponds to unstructured data and assigning the unstructured data to an unstructured data field of the electronic record. 
     
     
       10. The method of  claim 1 , comprising identifying, by the one or more processors from the speech data, at least one of a clinical note, cardiological procedure information, or orthopedic procedure information, and assigning, by the one or more processors to at least one field of the plurality of fields, the at least one of the clinical note, cardiological procedure information, or orthopedic procedure information. 
     
     
       11. A system, comprising:
 one or more processors configured to:
 receive chart data comprising a plurality of fields associated with at least one of an electronic health record, an electronic medical record, an electronic dental record, a practice management system record, or a treatment plan record; 
 identify a state of the chart data, the state comprising a selected field in the electronic record; 
 receive audio data; 
 apply a speech model to the audio data to generate a plurality of phrases from the audio data; 
 determine a first confidence value of a first phrase of the plurality of phrases based on spatial relationships between the state and the plurality of fields; 
 determine a second confidence value of a second phrase of the plurality of phrases based on the spatial relationships between the state and the plurality of fields; 
 select a command based on the first phrase responsive to the first confidence value being greater than the second confidence value; and 
 update the chart data based on the command. 
 
 
     
     
       12. The system of  claim 11 , wherein the one or more processors are configured to update the state responsive to assigning the at least one value. 
     
     
       13. The system of  claim 11 , wherein the one or more processors are configured to update the chart data by identifying a particular field of the plurality of fields based on the command and the state and assign the particular phrase to the particular field. 
     
     
       14. The system of  claim 11 , wherein the one or more processors are configured to apply at least one of text recognition or computer vision to an image representing the chart data to determine the state. 
     
     
       15. The system of  claim 14 , wherein the one or more processors are configured to generate a data object representing the electronic record responsive to applying the least one of text recognition or computer vision to the image. 
     
     
       16. The system of  claim 11 , wherein the one or more processors are configured to apply a signal indicative of at least one of a mouse movement or a keystroke to a client device to update the chart data. 
     
     
       17. The system of  claim 11 , wherein the one or more processors include a first processor operating on a client device and a second processor operating on a server device. 
     
     
       18. The system of  claim 11 , wherein the one or more processors are configured to apply the state as input to the speech model. 
     
     
       19. The system of  claim 11 , wherein the one or more processors are configured to determine that the at least one value corresponds to unstructured data and assign the unstructured data to an unstructured data field of the plurality of fields. 
     
     
       20. The system of  claim 11 , wherein the one or more processors are configured to identify, from the speech data, at least one of a clinical note, cardiological procedure information, or orthopedic procedure information, and assign, to at least one field of the plurality of fields, the at least one of the clinical note, cardiological procedure information, or orthopedic procedure information.